Highlights –

  • Even though AWS built its custom chips, Google Cloud chose to follow the lead of Azure by using Ampere chips.
  • The new VMs are already available in a few regions, including us-central (Iowa – Zone A, B, F), Asia-southeast1 (Singapore – Zone B, C), and Europe-west4 (Netherlands – Zone A, B, C). They will soon be coming to other data centers in the near future.

After the recent launch of Arm VMs (Virtual Machines) by Azure and Graviton instances by AWS, Google Cloud announced its first Arm-based VMs. Even though AWS built its custom chips, Google Cloud chose to follow the lead of Azure by using Ampere chips. The new VMs, in preview mode right now, is an addition to the line of Tau VMs under the ‘Tau T2A’ moniker. This line, which uses AMD Milan processors, was launched a year ago to offer a better price/performance ratio.

With each having up to 4GB memory, they will come in pre-defined SKUs having up to 48 vCPUs. The VMs will offer networking bandwidth of up to 32 Gbps and support the usual range of storage options available in the Google Cloud ecosystem. According to Google, these CPU specs make the machines suitable for various workloads, including web servers, containerized microservices, data-logging apps, and more.

Google considers these chips its price-performance optimized solution, just like AMD-powered Tau chips. For instance, a 32-core Tau T2A CM will cost USD 1.232 per hour in the us-central1 region of Google Cloud.

In addition to Google’s Container-Optimized OS for running containerized applications, users will also be able to use similar kinds of CentOS, Rocky Linux, RHEL, and Ubuntu on these machines. Arm support has set the bar high for most software and OS vendors, which helps enhance the functionality of these VMs.

The new VMs are already available in a few regions, including US – central (Iowa – Zone A, B, F), Asia – Southeast1 (Singapore – Zone B, C), and Europe – west4 (Netherlands – Zone A, B, C). They will soon be coming to other data centers. Jeff Wittich, Chief Product Officer, Ampere Computing, expressed, “Ampere Altra Cloud Native Processors were designed from the ground up to meet the demands of modern cloud applications. Our close collaboration with Google Cloud has resulted in the launch of the new price-performance optimized Tau T2A instances, which enable demanding scale-out applications be deployed rapidly and efficiently.”

In addition to considering VMs part of Google Cloud’s Computer Engine, the tech giant will also support them as part of its Kubernetes Engine, Dataflow stream and batch processing services, and a new complete job scheduler named Batch.

Experts’ Take

Sachin Gupta, Google Cloud’s VP and GM for infrastructure, said, “We are excited to extend the rich choices we already offer with Intel and AMD and enter the Arm ecosystem to provide our customers with even more choice and flexibility. We have support for a broad ecosystem of operating systems, databases, programming languages, and other tools.”

He added, “This new capability will benefit major use cases for throughput-oriented computing such as weather forecasting and electronic design automation. The primary purpose of this new service is to offer unprecedented flexibility in time, location, and cost of cloud capacity for batch jobs.”